© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11363
    Prev
    Next
    INDEX
    Explanations

    free and open source

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically detects the word “free” (as in free events, services, or offers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    G
    1.27
    I
    1.20
    ，
    1.19
    Ciao
    1.14
    ㈤
    1.14
    ian
    1.11
    Gesch
    1.09
    Voir
    1.07
     годов
    1.07
     бывает
    1.06
    POSITIVE LOGITS
     gratis
    1.48
    bies
    1.38
    bie
    1.22
    いた
    1.20
    🆓
    1.20
     gratuita
    1.17
    yed
    1.17
     무료
    1.15
    তে
    1.13
     Free
    1.11
    Activations Density 0.056%

    No Known Activations